论文python复现：Ordinal regression by extended binary classification

L. Li and H.-T. Lin, ‘‘Ordinal regression by extended binary classification,’’ in Proc. Adv. Neural Inf. Process. Syst., 2007, pp. 865–872
基于cvxpy实现了个线性版的

要点：cvxpy中连续多个约束可以使用for循环得到，详细见代码41行。

目前是草稿版，只计算出了各个参数：

import numpy as np
from sklearn import datasets
import cvxpy as cp

class eSVM():
    def __init__(self,X_train,y_train):
        self.X = X_train
        self.y = y_train
        self.n_features = X_train.shape[1]
        self.n_instances = X_train.shape[0]
        self.n_class = len(set(self.y))
        self.n_theta = self.n_class - 1

        self.w = cp.Variable((self.n_features,1))
        self.b = cp.Variable()
        self.xi = cp.Variable((self.n_instances, self.n_theta))

        self.theta = cp.Variable((1,self.n_class-1))

        self.C = 1
        self.Y = self.rcon_label()

    def rcon_label(self):
        target = []
        for i in range(self.n_instances):
            label = []
            for j in range(self.n_theta):
                if self.y[i] <= j:
                    a = 1
                else:
                    a = 0
                label.append(1 - 2 * a)
            target.append(label)
        return np.array(target)

    def optimal(self):
        #TODO:np.tile(self.theta,(self.n_instances,1))写错了
        objective = cp.Minimize(0.5 * cp.norm2(self.w) + 0.5 * cp.norm(self.theta) + self.C * cp.sum(self.xi))

        constraints = []
        for i in range(self.n_instances):
            for k in range(self.n_theta):
                constraints += [self.Y[i,k] * cp.sum(cp.multiply(self.X[1].reshape(-1,1), self.w)) - self.Y[i, k] * self.theta[0][k] - self.Y[i,k] * self.b >= 1 - self.xi[i,k], self.xi[i,k]>=0]

        prob = cp.Problem(objective, constraints)
        result = prob.solve()
        # print(prob.value)
        print("w=",self.w.value)
        print("b=",self.b.value)
        print("theta=",self.theta.value)


if __name__ == '__main__':
    X, y = datasets.make_blobs(n_samples=100, n_features=2, center_box=(-20, 20), centers=4, cluster_std=[4, 4, 4, 4], random_state=3)
    print("数据类别信息",np.unique(y))
    for i, ele in enumerate(y):
        if ele == 3:
            y[i] = 0
        elif ele == 0:
            y[i] = 2
        elif ele == 2:
            y[i] = 3

    model = eSVM(X_train=X,y_train=y)
    model.optimal()

标签：Ordinal,binary,extended,self,train,__,print,theta,cp
来源： https://blog.csdn.net/DeniuHe/article/details/112267985